ukidZddlZddlmZddlZddlmZddlmZddlm Z ddl m Z ddl m Z dd l mZdd l mZdd l mZdd l mZdd l mZddlmZddlmZddlmZddlmZddlmZddlmZddlmZddlmZddlmZddlmZddl m!Z!ddl"m#Z#ddl$m%Z%GddejLZ'dZ(dZ)Gdd e!Z*y)!zMediaPipe Pose.N) NamedTuple)#constant_side_packet_calculator_pb2)gate_calculator_pb2)split_vector_calculator_pb2)warp_affine_calculator_pb2)image_to_tensor_calculator_pb2)inference_calculator_pb2)(tensors_to_classification_calculator_pb2)$tensors_to_detections_calculator_pb2)#tensors_to_landmarks_calculator_pb2)&tensors_to_segmentation_calculator_pb2)ssd_anchors_calculator_pb2)"detections_to_rects_calculator_pb2)"landmarks_smoothing_calculator_pb2)"local_file_contents_calculator_pb2)logic_calculator_pb2)"non_max_suppression_calculator_pb2)"rect_transformation_calculator_pb2)thresholding_calculator_pb2)#visibility_smoothing_calculator_pb2)switch_container_pb2) SolutionBase)download_utils)POSE_CONNECTIONSceZdZdZdZdZdZdZdZdZ dZ d Z d Z d Z d Zd ZdZdZdZdZdZdZdZdZdZdZdZdZdZdZdZdZdZ dZ!d Z"d!Z#d"Z$y#)$ PoseLandmarkzThe 33 pose landmarks.r  N)%__name__ __module__ __qualname____doc__NOSELEFT_EYE_INNERLEFT_EYELEFT_EYE_OUTERRIGHT_EYE_INNER RIGHT_EYERIGHT_EYE_OUTERLEFT_EAR RIGHT_EAR MOUTH_LEFT MOUTH_RIGHT LEFT_SHOULDERRIGHT_SHOULDER LEFT_ELBOW RIGHT_ELBOW LEFT_WRIST RIGHT_WRIST LEFT_PINKY RIGHT_PINKY LEFT_INDEX RIGHT_INDEX LEFT_THUMB RIGHT_THUMBLEFT_HIP RIGHT_HIP LEFT_KNEE RIGHT_KNEE LEFT_ANKLE RIGHT_ANKLE LEFT_HEEL RIGHT_HEELLEFT_FOOT_INDEXRIGHT_FOOT_INDEXZ/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/mediapipe/python/solutions/pose.pyrr5s $. (./)/ ()*+-.*+*+*+*+*+ ())**+)*/rcrz:mediapipe/modules/pose_landmark/pose_landmark_cpu.binarypbcp|dk(rtjdy|dk(rtjdyy)zoDownloads the pose landmark lite/heavy model from the MediaPipe Github repo if it doesn't exist in the package.rz9mediapipe/modules/pose_landmark/pose_landmark_lite.tfliterz:mediapipe/modules/pose_landmark/pose_landmark_heavy.tfliteN)rdownload_oss_model)model_complexitys rd!_download_oss_pose_landmark_modelrh]s=%%CE1%%DFrccZeZdZdZ dfd Zdej deffd ZxZ S)PosezMediaPipe Pose. MediaPipe Pose processes an RGB image and returns pose landmarks on the most prominent person detected. Please refer to https://solutions.mediapipe.dev/pose#python-solution-api for usage examples. c vt|t| t||xr| ||xr| | d||dgdy)ajInitializes a MediaPipe Pose object. Args: static_image_mode: Whether to treat the input images as a batch of static and possibly unrelated images, or a video stream. See details in https://solutions.mediapipe.dev/pose#static_image_mode. model_complexity: Complexity of the pose landmark model: 0, 1 or 2. See details in https://solutions.mediapipe.dev/pose#model_complexity. smooth_landmarks: Whether to filter landmarks across different input images to reduce jitter. See details in https://solutions.mediapipe.dev/pose#smooth_landmarks. enable_segmentation: Whether to predict segmentation mask. See details in https://solutions.mediapipe.dev/pose#enable_segmentation. smooth_segmentation: Whether to filter segmentation across different input images to reduce jitter. See details in https://solutions.mediapipe.dev/pose#smooth_segmentation. min_detection_confidence: Minimum confidence value ([0.0, 1.0]) for person detection to be considered successful. See details in https://solutions.mediapipe.dev/pose#min_detection_confidence. min_tracking_confidence: Minimum confidence value ([0.0, 1.0]) for the pose landmarks to be considered tracked successfully. See details in https://solutions.mediapipe.dev/pose#min_tracking_confidence. )rgsmooth_landmarksenable_segmentationsmooth_segmentationuse_prev_landmarks)z@posedetectioncpu__TensorsToDetectionsCalculator.min_score_threshz]poselandmarkbyroicpu__tensorstoposelandmarksandsegmentation__ThresholdingCalculator.threshold)pose_landmarkspose_world_landmarkssegmentation_mask)binary_graph_path side_inputscalculator_paramsoutputsN)rhsuper__init___BINARYPB_FILE_PATH) selfstatic_image_modergrlrmrnmin_detection_confidencemin_tracking_confidence __class__s rdrxz Pose.__init__rs`>&&67 G- 0 0 J9J5J#6#=,=(=&7"7  )'  P!Qrcimagereturnc t|d|i}|jr,|jjD]}|j d|j r,|j jD]}|j d|S)aProcesses an RGB image and returns the pose landmarks on the most prominent person detected. Args: image: An RGB image represented as a numpy ndarray. Raises: RuntimeError: If the underlying graph throws any error. ValueError: If the input image is not three channel RGB. Returns: A NamedTuple with fields describing the landmarks on the most prominate person detected: 1) "pose_landmarks" field that contains the pose landmarks. 2) "pose_world_landmarks" field that contains the pose landmarks in real-world 3D coordinates that are in meters with the origin at the center between hips. 3) "segmentation_mask" field that contains the segmentation mask if "enable_segmentation" is set to true. r) input_datapresence)rwprocessrplandmark ClearFieldrq)rzrresultsrr~s rdrz Pose.processs*go'5)9o:G,,55((J'(##22;;((J'( Nrc)FrTFT?r) r=r>r?r@rxnpndarrayrr __classcell__)r~s@rdrjrjhsB"' ! $#(#'(+'*0Qd2::*rcrj)+r@enumtypingrnumpyrmediapipe.calculators.corerrrmediapipe.calculators.imagermediapipe.calculators.tensorrr r r r r mediapipe.calculators.tflitermediapipe.calculators.utilrrrrrrrrmediapipe.framework.toolrmediapipe.python.solution_basermediapipe.python.solutionsr+mediapipe.python.solutions.pose_connectionsrIntEnumrryrhrjrbrcrdrs  K:BBGAQMLOCIII;IIBJ975H"4<<"JSFX<Xrc